Method and device for predicting health state of lithium battery of automobile, vehicle and medium

Abstract

The invention relates to a method and device for predicting the health state of a lithium battery of an automobile, a vehicle and a medium, and the method comprises the steps: collecting at least one data of the voltage, current and temperature of the lithium battery and the speed and mileage of the vehicle; extracting a voltage change rate, a current peak value and temperature fluctuation from the at least one item of data, and preprocessing the voltage change rate, the current peak value and the temperature fluctuation to generate preprocessed data; and extracting at least one key feature from the preprocessed data, and inputting the at least one key feature into a pre-constructed linear regression prediction model, so as to predict the health state of the lithium battery in real time by using the pre-constructed linear regression prediction model, and generate a health state prediction result. According to the embodiment of the invention, various data in the running process of the lithium battery can be collected in real time, the prediction accuracy is improved, and the linear regression model is arranged, so that the system is simple in structure, easy to understand and implement and suitable for various prediction scenes.

Description

Technical Field

[0001] The present application relates to the field of battery monitoring technology, and in particular to a method, device, vehicle and medium for predicting the health status of a lithium battery of an automobile. Background Art

[0002] Artificial intelligence refers to the technology and methods of simulating and realizing human intelligence through computer programs or machines. This technology enables computers to have human-like intelligence capabilities such as perception, understanding, judgment, reasoning, learning, recognition, generation, and interaction, so that they can perform various tasks. Its core is algorithms such as machine learning and deep learning. These algorithms enable computers to automatically discover patterns in data through large amounts of data and training, and perform operations such as pattern recognition, classification, and prediction. Among them, with the continuous development of the automotive industry, the performance and service life of its lithium batteries are relatively important. The health status of automotive lithium-ion batteries is an important indicator of their remaining capacity and performance. However, during the use of some vehicles, due to the inconsistency between single cells, the battery pack is prone to imbalance during the charging and discharging process, resulting in overcharging or over-discharging of some batteries, reducing the overall performance and life of the battery pack. At the same time, the operating efficiency and maintenance cost of the vehicle are directly affected by the health of the battery. The decline in battery performance will lead to a shortened driving range and an increase in the number of charging times, thereby reducing operating efficiency and increasing maintenance costs. Active balancing and passive balancing are mainly used to solve the above problems. Active balancing refers to balancing through a circuit structure composed of circuits and control chips to achieve power transfer between single cells, so that the voltage and capacity of each single cell are as close to the same as possible. Passive balancing refers to discharging single cells with higher voltages through resistance discharge and other methods without changing the battery state, releasing electricity in the form of heat, and buying more charging time for other batteries.

[0003] In the related art, common methods for solving the prediction of lithium battery health status may include methods based on physical models and methods based on empirical formulas. The general steps of the method based on physical models are: first establish an equivalent circuit model or electrochemical model of the lithium battery, and then measure the battery's voltage, current and other parameters, and substitute them into the model for calculation and analysis. The technical conditions required for implementation include accurate battery parameter measurement equipment and actual parameters such as the open circuit voltage and internal resistance of the battery. The general steps of the method based on empirical formulas are: through the accumulation of a large amount of experimental data, establish an empirical relationship between battery performance indicators and health status. Parameters that need to be measured in practical applications include the number of battery cycles, depth of discharge, etc.

[0004] However, in the related art, for the physical model-based method: the model is complex, the calculation amount is large, the measurement accuracy requirements for battery parameters are extremely high, and the accuracy of the model is affected by various factors, such as battery aging, temperature change, etc., and it is difficult to accurately reflect the true health state of the battery in practical applications. For the empirical formula-based method: it is overly dependent on experimental data, and the generality is poor. Lithium batteries of different types and under different usage conditions may require re-establishing empirical formulas, and it cannot capture the complex chemical and physical change processes inside the battery, and the prediction accuracy is limited, which urgently needs to be improved. Summary of the Invention

[0005] The present application provides a method, a device, a vehicle and a medium for predicting the health state of a lithium battery of an automobile, so as to solve the problems in the related art that for the physical model-based method: the model is complex, the calculation amount is large, the measurement accuracy requirements for battery parameters are extremely high, and the accuracy of the model is affected by various factors, such as battery aging, temperature change, etc., and it is difficult to accurately reflect the true health state of the battery in practical applications. For the empirical formula-based method: it is overly dependent on experimental data, and the generality is poor. Lithium batteries of different types and under different usage conditions may require re-establishing empirical formulas, and it cannot capture the complex chemical and physical change processes inside the battery, and the prediction accuracy is limited.

[0006] The first aspect embodiment of the present application provides a method for predicting the health state of a lithium battery of an automobile, including the following steps: collecting at least one item of data of the voltage, current, and temperature of the lithium battery and the speed and mileage of the vehicle; extracting the voltage change rate, current peak value, and temperature fluctuation from the at least one item of data, and preprocessing the voltage change rate, the current peak value, and the temperature fluctuation to generate preprocessed data; extracting at least one key feature from the preprocessed data, and inputting the at least one key feature into a pre-constructed linear regression prediction model to use the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result.

[0007] Optionally, in an embodiment of the present application, after using the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result, it further includes: judging whether the lithium battery has a fault according to the health state prediction result; if the lithium battery has a fault, monitoring the fault state of the lithium battery, and generating a fault diagnosis report of the lithium battery according to the fault state; generating at least one fault warning message of the vehicle according to the fault diagnosis report, and prompting the driver of the fault state of the lithium battery according to the at least one fault warning message.

[0008] Optionally, in an embodiment of the present application, the method for using the pre-constructed linear regression prediction model to predict the state of health of the lithium battery in real time and generate a state of health prediction result includes: integrating the lithium battery management system of the vehicle with the lithium battery management system of the target vehicle to generate an integration result; based on the integration result, evaluating the state of health of the lithium battery according to the overall operating condition data of the vehicle to generate evaluation data; adjusting the parameters of the pre-constructed linear regression prediction model according to the evaluation data to generate adjusted parameters, and using the adjusted parameters to predict the state of health of the lithium battery in real time to generate the state of health prediction result.

[0009] Optionally, in an embodiment of the present application, after collecting at least one of the voltage, current, and temperature of the lithium battery, it further includes: encrypting the at least one data to generate encrypted data; storing the encrypted data in a preset database to use the preset database to back up the encrypted data according to a target period to generate backed-up data; transmitting the backed-up data to the cloud to communicate with the target vehicle.

[0010] Optionally, in an embodiment of the present application, the method for preprocessing the voltage change rate, the current peak value, and the temperature fluctuation to generate preprocessed data includes: performing data cleaning on the voltage change rate, the current peak value, and the temperature fluctuation to generate cleaned data; screening the cleaned data to generate data that meets preset normal conditions; formatting the data that meets the preset normal conditions to generate the preprocessed data.

[0011] An embodiment of the second aspect of the present application provides a device for predicting the state of health of a lithium battery of an automobile, including: a collection module, configured to collect at least one of the voltage, current, and temperature of the lithium battery and the speed and mileage of the vehicle; a preprocessing module, configured to extract the voltage change rate, the current peak value, and the temperature fluctuation from the at least one data, and preprocess the voltage change rate, the current peak value, and the temperature fluctuation to generate preprocessed data; a prediction module, configured to extract at least one key feature from the preprocessed data, and input the at least one key feature into a pre-constructed linear regression prediction model to use the pre-constructed linear regression prediction model to predict the state of health of the lithium battery in real time and generate a state of health prediction result.

[0012] Optionally, in an embodiment of the present application, it further includes: a judgment module, configured to judge whether there is a fault in the lithium battery according to the health status prediction result after using the pre-constructed linear regression prediction model to predict the health status of the lithium battery in real time and generating a health status prediction result; a monitoring module, configured to monitor the fault status of the lithium battery if there is a fault in the lithium battery, and generate a fault diagnosis report of the lithium battery according to the fault status; a prompting module, configured to generate at least one fault warning message of the vehicle according to the fault diagnosis report, and prompt the driver of the fault status of the lithium battery according to the at least one fault warning message.

[0013] Optionally, in an embodiment of the present application, the prediction module includes: an integration unit, configured to integrate the lithium battery management system of the vehicle and the lithium battery management system of the target vehicle to generate an integration result; an evaluation unit, configured to evaluate the health status of the lithium battery according to the overall operation condition data of the vehicle based on the integration result to generate evaluation data; a prediction unit, configured to adjust the parameters of the pre-constructed linear regression prediction model according to the evaluation data to generate adjusted parameters, and use the adjusted parameters to predict the health status of the lithium battery in real time to generate the health status prediction result.

[0014] Optionally, in an embodiment of the present application, it further includes: an encryption module, configured to encrypt at least one of the voltage, current, and temperature data of the lithium battery after collecting the at least one data to generate encrypted data; a storage module, configured to store the encrypted data in a preset database to use the preset database to back up the encrypted data according to a target period to generate backed-up data; a communication module, configured to transmit the backed-up data to the cloud to communicate with the target vehicle.

[0015] Optionally, in an embodiment of the present application, the preprocessing module includes: a cleaning unit, configured to perform data cleaning on the voltage change rate, the current peak value, and the temperature fluctuation to generate cleaned data; a screening unit, configured to screen the cleaned data to generate data that meets preset normal conditions; a generating unit, configured to format the data that meets the preset normal conditions to generate the preprocessed data.

[0016] An embodiment of the third aspect of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the method for predicting the health status of the lithium battery of the vehicle as described in the above embodiment.

[0017] The fourth aspect of the present application provides a computer-readable storage medium that stores a computer program. When the program is executed by a processor, it implements the method for predicting the health state of a lithium battery of an automobile as described above.

[0018] Embodiments of the present application can collect various data during the operation of the lithium battery in real time, improve the accuracy of prediction, monitor the fault state of the lithium battery in real time, provide a fault diagnosis report, and send a warning message to the driver or maintenance personnel after detecting a potential fault or confirming a fault, so that the fault of the lithium battery can be discovered and processed in time, improving the safety and reliability of the vehicle. And by setting a linear regression model in the present application, its structure is simple, easy to understand and implement, applicable to various prediction scenarios. At the same time, the model parameters have clear physical meanings and can explain the influence degree of independent variables on dependent variables. In the case of moderate data volume, it has good stability and generalization ability. Thus, it solves the problems in the related technologies. For the method based on the physical model: the model is complex, the calculation amount is large, the measurement accuracy requirements for battery parameters are extremely high, and the accuracy of the model is affected by various factors, such as battery aging, temperature change, etc., and it is difficult to accurately reflect the true health state of the battery in practical applications. For the method based on the empirical formula: it is too dependent on experimental data, the generality is poor, lithium batteries of different types and different usage conditions may require re-establishing empirical formulas, and it cannot capture the complex chemical and physical change processes inside the battery, and the prediction accuracy is limited.

[0019] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0020] The above and / or additional aspects and advantages of the present application will become apparent and be easily understood from the following description of the embodiments in conjunction with the drawings, where:

[0021] Figure 1 is a flowchart of a method for predicting the health state of a lithium battery of an automobile according to an embodiment of the present application;

[0022] Figure 2 is a schematic structural diagram of a method for predicting the health state of a lithium battery of an automobile according to an embodiment of the present application;

[0023] Figure 3 is a schematic connection diagram of a method for predicting the health state of a lithium battery of an automobile according to an embodiment of the present application;

[0024] Figure 4 is a schematic diagram of system integration and coordination of a method for predicting the health state of a lithium battery of an automobile according to an embodiment of the present application;

[0025] Figure 5Schematic diagram of state monitoring and data preprocessing for the method of predicting the health state of a lithium battery of an automobile according to an embodiment of the present application;

[0026] Figure 6 Flow schematic diagram of the method of predicting the health state of a lithium battery of an automobile according to an embodiment of the present application;

[0027] Figure 7 Schematic structural diagram of a device for predicting the health state of a lithium battery of an automobile provided according to an embodiment of the present application;

[0028] Figure 8 Schematic structural diagram of a vehicle provided according to an embodiment of the present application. Detailed implementation manners

[0029] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as a limitation of the present application.

[0030] The following describes a method, device, vehicle, and medium for predicting the health state of a lithium battery of a vehicle according to an embodiment of the present application. In view of the problems in the related art mentioned in the above background art, for the method based on a physical model: the model is complex, the calculation amount is large, the measurement accuracy requirements for battery parameters are extremely high, and the accuracy of the model is affected by various factors, such as battery aging, temperature change, etc., and it is difficult to accurately reflect the true health state of the battery in practical applications. For the method based on an empirical formula: it is too dependent on experimental data, the generality is poor, different types and different usage conditions of lithium batteries may require re-establishing empirical formulas, and it cannot capture the complex chemical and physical change processes inside the battery, and the prediction accuracy is limited. The present application provides a method for predicting the health state of a lithium battery of a vehicle. In this method, various data during the operation of the lithium battery can be collected in real time to improve the accuracy of prediction, the fault state of the lithium battery can be monitored in real time, a fault diagnosis report can be provided, and a warning message can be sent to the driver or maintenance personnel after detecting a potential fault or confirming a fault, so that the faults of the lithium battery can be discovered and processed in time, improving the safety and reliability of the vehicle. And the present application sets up a linear regression model, which has a simple structure, is easy to understand and implement, is applicable to various prediction scenarios, and at the same time, the model parameters have clear physical meanings and can explain the influence degree of independent variables on dependent variables. In the case of moderate data volume, it has good stability and generalization ability. Thus, the problems in the related art are solved, that is, for the method based on a physical model: the model is complex, the calculation amount is large, the measurement accuracy requirements for battery parameters are extremely high, and the accuracy of the model is affected by various factors, such as battery aging, temperature change, etc., and it is difficult to accurately reflect the true health state of the battery in practical applications. For the method based on an empirical formula: it is too dependent on experimental data, the generality is poor, different types and different usage conditions of lithium batteries may require re-establishing empirical formulas, and it cannot capture the complex chemical and physical change processes inside the battery, and the prediction accuracy is limited, etc.

[0031] Specifically, Figure 1 FIG. is a schematic flowchart of a method for predicting the health state of a lithium battery of a vehicle provided by an embodiment of the present application.

[0032] As Figure 1 shown, the method for predicting the health state of a lithium battery of the vehicle includes the following steps:

[0033] In step S101, at least one piece of data among the voltage, current, and temperature of the lithium battery and the speed and mileage of the vehicle is collected.

[0034] In the actual execution process, the embodiment of the present application can collect various data during the operation of the lithium battery, and use the sensor network on the vehicle to record the voltage, current, temperature of the lithium battery, and auxiliary information such as the vehicle speed and mileage in real time, providing a rich data basis for subsequent prediction.

[0035] The embodiments of the present application can collect various data during the operation of a lithium battery in real time to improve the accuracy of subsequent predictions. At the same time, the data collected by multiple sensors can comprehensively reflect the operating state of the lithium battery, including multiple dimensions such as voltage, current, and temperature. Moreover, the data collection process is automated, reducing manual intervention and improving the efficiency and accuracy of data collection.

[0036] Optionally, in an embodiment of the present application, after collecting at least one of the voltage, current, and temperature of the lithium battery, it further includes: encrypting at least one of the data to generate encrypted data; storing the encrypted data in a preset database to use the preset database to back up the encrypted data according to a target period to generate backed-up data; and transmitting the backed-up data to the cloud to communicate with a target vehicle.

[0037] Among them, the embodiments of the present application can perform data encryption, decryption, and access control to ensure data security. Encrypt at least one of the data to generate encrypted data, and store the encrypted data in a preset database to achieve fast access and efficient management of the data. Use the preset database to back up the data regularly or on demand to generate backed-up data to prevent data loss or damage. In the process of predicting the health of the lithium battery, the embodiments of the present application can transmit the backed-up data to the cloud to communicate with the target vehicle, realize communication, data exchange, and synchronization with other vehicle systems, and coordinate the operation of each system according to the health state of the lithium battery and the state of other vehicle systems. When a system failure occurs, quickly isolate the fault source and take recovery measures.

[0038] As Figure 2 shown, the embodiments of the present application can set a data storage function to store various data generated by the system, ensure storage efficiency, security, and reliability, and at the same time ensure the effective utilization of the data. By setting a communication function, the transmission operations between various functions and between the system and external devices can be ensured, and the accurate transmission and reception of data can be ensured.

[0039] In step S102, extract the voltage change rate, current peak value, and temperature fluctuation from at least one of the data, and preprocess the voltage change rate, current peak value, and temperature fluctuation to generate preprocessed data.

[0040] Specifically, the embodiments of the present application can extract the original data of the voltage change rate, current peak value, and temperature fluctuation from the original data such as the voltage, current, and temperature of the lithium battery, and then preprocess them to generate preprocessed data.

[0041] The embodiments of the present application can extract key features from the preprocessed data, and select the features that have the greatest impact on the prediction result as the model input, which can reduce the complexity and computational amount of the model, and improve the prediction efficiency and accuracy.

[0042] Optionally, in an embodiment of the present application, the voltage change rate, current peak value, and temperature fluctuation are preprocessed to generate preprocessed data, including: performing data cleaning on the voltage change rate, current peak value, and temperature fluctuation to generate cleaned data; screening the cleaned data to generate data that meets the preset normal conditions; formatting the data that meets the preset normal conditions to generate preprocessed data.

[0043] It can be understood that the data that meets the preset normal conditions in the embodiments of the present application can be normal data after removing outliers.

[0044] In the actual execution process, the embodiments of the present application can perform data cleaning on the voltage change rate, current peak value, and temperature fluctuation to generate cleaned data, screen the cleaned data to generate normal data, and format the normal data to generate preprocessed data.

[0045] As Figure 2 shown, the embodiments of the present application can effectively remove noise, outliers, and duplicate records through data analysis and prediction functions, improve data quality, provide a reliable data basis for subsequent prediction models, and at the same time, according to the prediction requirements, screen out the data useful for predicting the health state of lithium batteries, reduce data redundancy, improve processing efficiency. After converting the data into a unified format, it is convenient for subsequent analysis and modeling work. At the same time, key features that can reflect the health state of lithium batteries can be extracted from the original data, providing effective input for the prediction model. At the same time, through methods such as correlation analysis, the features that have the greatest impact on the prediction result are selected, reducing the model complexity and improving the prediction efficiency.

[0046] In step S103, at least one key feature is extracted from the preprocessed data, and the at least one key feature is input into a pre-constructed linear regression prediction model to use the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result.

[0047] Among them, the embodiments of the present application can extract features useful for predicting the health state of lithium batteries from the preprocessed data, analyze the extracted features using machine learning algorithms or statistical methods, analyze the change trend and potential failure modes of the health state of lithium batteries, and based on the results of data analysis, use a linear regression algorithm to predict the health state of lithium batteries, including the remaining life and the performance degradation rate, etc. By inputting the selected features into the linear regression prediction model, the health state index of the lithium battery is calculated to use the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result. The embodiments of the present application use a linear regression prediction model to predict the health state of the lithium battery in real time and evaluate based on the prediction result, evaluate the health state of the lithium battery based on the prediction result, and provide a scientific basis for vehicle maintenance and battery replacement. Verify the prediction result according to the actual use situation and continuously optimize the linear regression model and the feature selection process. Continuously optimize the linear regression model and the feature selection process according to the feedback result, continuously improve the performance and adaptability of the prediction model, and ensure its accuracy and stability in different usage scenarios.

[0048] The embodiments of the present application can set a linear regression model, which has a simple structure, is easy to understand and implement, is applicable to a variety of prediction scenarios, and at the same time, the model parameters have clear physical meanings and can explain the influence degree of independent variables on dependent variables. In the case of moderate data volume, it has good stability and generalization ability, can accurately predict the health state of lithium batteries, and improve the service life and performance of lithium batteries.

[0049] Optionally, in an embodiment of the present application, after using the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result, it further includes: judging whether the lithium battery has a fault according to the health state prediction result; if the lithium battery has a fault, monitoring the fault state of the lithium battery and generating a fault diagnosis report of the lithium battery according to the fault state; generating at least one fault warning information of the vehicle according to the fault diagnosis report and prompting the driver of the fault state of the lithium battery according to the at least one fault warning information.

[0050] During the actual implementation process, the embodiments of the present application can determine whether there is a fault in the lithium battery according to the health status prediction result. For example, according to a preset threshold or a machine learning-based method, it is determined whether there is a fault or a potential fault in the lithium battery. If there is a fault in the lithium battery, the cause of the fault is further analyzed, the fault status of the lithium battery is monitored, and a fault diagnosis report of the lithium battery is generated according to the fault status. At least one fault warning message of the vehicle is generated according to the fault diagnosis report, and a warning message is sent to the driver or maintenance personnel according to the at least one fault warning message. At the same time, corresponding countermeasures are taken, such as adjusting the charge and discharge strategy, restricting vehicle use, etc. At the same time, the charge and discharge process of the lithium battery pack is intelligently controlled, the charge and discharge currents of each single battery are balanced, and the battery pack is protected from damage. Under the action of the charge and discharge control function, the charge and discharge strategy can be adjusted to optimize the battery performance and service life. Under the action of the balance control function, the charge balance between each single battery is ensured to prevent overcharging or over-discharging. Under the action of the protection control function, various parameters of the battery pack are monitored to ensure that the battery operates within a safe range.

[0051] As Figure 2 shown, the embodiments of the present application can, through the fault management function, monitor the fault status of the lithium battery in real time, provide a fault diagnosis report, and send a warning message to the driver or maintenance personnel after detecting a potential fault or confirming a fault, so that the fault of the lithium battery can be discovered and processed in time, improving the safety and reliability of the vehicle.

[0052] Optionally, in an embodiment of the present application, a pre-constructed linear regression prediction model is used to predict the health status of the lithium battery in real time and generate a health status prediction result, including: integrating the lithium battery management system of the vehicle with the lithium battery management system of the target vehicle to generate an integration result; based on the integration result, evaluating the health status of the lithium battery according to the overall operation condition data of the vehicle to generate evaluation data; adjusting the parameters of the pre-constructed linear regression prediction model according to the evaluation data to generate adjusted parameters, and using the adjusted parameters to predict the health status of the lithium battery in real time to generate a health status prediction result.

[0053] It can be understood that the target vehicle in the embodiments of the present application can be other vehicles.

[0054] As a possible implementation manner, as Figure 2 shown, the embodiments of the present application can integrate the lithium battery management system of the vehicle with the lithium battery management system of other vehicles through the system integration and coordination function to generate an integration result. Based on the integration result, the health status of the lithium battery is evaluated according to the overall operation condition data of the vehicle to generate evaluation data. The parameters of the pre-constructed linear regression prediction model are adjusted according to the evaluation data to generate adjusted parameters, and the adjusted parameters are used to predict the health status of the lithium battery in real time to generate a health status prediction result.

[0055] Embodiments of the present application can coordinate the operation of each system according to the health state of the lithium battery and the states of other vehicle systems, improve the overall performance and efficiency of the vehicle, and also help to quickly isolate the fault source and take recovery measures in case of a failure to ensure the normal operation of the vehicle.

[0056] Specifically, it can be combined with Figures 3 to 6 As shown, the working principle of the lithium battery health state prediction method for an automobile in the embodiments of the present application will be elaborated in detail with a specific embodiment.

[0057] As Figure 3 shown, the control functions include a total control function, a charge and discharge control function, a balance control function, and a protection control function. The total control function is connected to the charge and discharge control function, the balance control function, and the protection control function. The total control function is used to connect and control each function. The charge and discharge control function is used to intelligently control the charge and discharge process of the lithium battery pack according to the data of the fault management unit. The balance control function is used to adjust the charge and discharge current of each single battery to maintain the charge balance between the batteries. The protection control function is used to monitor various parameters of the battery pack; dividing the control function into functions such as charge and discharge control, balance control, and protection control improves the flexibility and maintainability of the system. The total control function, as the core, coordinates the work of each sub-function to ensure the efficient operation of the entire system. The charge and discharge control function can intelligently adjust the charge and discharge process according to the monitored data, improving the battery usage efficiency and safety. The protection control function monitors the battery pack parameters in real time to ensure that the battery operates within a safe range.

[0058] The fault management functions include a state monitoring function, a fault detection function, a fault prediction function, and a warning and response function. The state monitoring function is connected to the fault detection function. The fault detection function is connected to the fault prediction function. The fault prediction function is connected to the warning and response function. The warning and response function is connected to the protection control function. The state monitoring function is used to monitor the key state parameters of the lithium battery in real time to ensure the accuracy and timeliness of the data. The fault detection function is used to determine whether the lithium battery has a fault according to a preset threshold or a machine learning-based method. The fault prediction function is used to further analyze the cause of the fault and provide a fault diagnosis report after detecting the fault. The warning and response function is used to send a warning message to the driver or maintenance personnel and take corresponding countermeasures after detecting a potential fault or confirming a fault; through multi-dimensional monitoring such as voltage, current, and temperature, it can comprehensively reflect the operating state of the lithium battery and collect data in real time, providing timely and accurate information for the control function and the data analysis and prediction function. Through the collaborative work of functions such as state monitoring, fault detection, fault prediction, and warning and response, potential faults can be detected and processed in a timely manner to ensure the reliability and safety of the lithium battery system.

[0059] The data analysis and detection functions include data preprocessing function, feature extraction function, data analysis function, update and adaptation function, and health status prediction function. The data preprocessing function is connected to the feature extraction function, the feature extraction function is connected to the data analysis function, the data analysis function is connected to the update and adaptation function, and the update and adaptation function is connected to the health status prediction function. The data preprocessing function is used to perform preprocessing such as cleaning, screening, and formatting on the collected data. The feature extraction function is used to extract feature data useful for predicting the health status of lithium batteries from the preprocessed data. The data analysis function is used to analyze the extracted feature data. The update and adaptation function is used to update the model parameters in real time according to newly collected data to adapt to the changes in the health status of lithium batteries. The health status prediction function is used to predict the health status of lithium batteries based on the results of data analysis using intelligent algorithms. Through steps such as data preprocessing, feature extraction, and data analysis, useful information related to the health status of lithium batteries can be deeply mined. The update and adaptation function can update the model parameters in real time, adapt to the changes in the health status of lithium batteries, and improve the accuracy of prediction. The health status prediction function then uses intelligent algorithms to predict the health status of lithium batteries, providing a scientific basis for battery maintenance and replacement.

[0060] The data storage function includes data security function, data storage function, database, and data backup function. The data security function is connected to the data storage function, and the data storage function is connected to both the database and the data backup function. The data security function is responsible for data encryption, decryption, and access control. The data storage function is used for... The data backup function is used to back up data regularly or on demand. The database is used to store the generated data. The data security function ensures data encryption, decryption, and access control, protecting the data from being illegally obtained or tampered with. The combination of the data storage function and the database enables fast access and efficient management of data. The data backup function backs up data regularly or on demand to prevent data loss or damage.

[0061] The system integration and coordination functions include interface standardization function, data exchange and synchronization function, system coordination function, and fault isolation and recovery function. The interface standardization function is connected to the data exchange and synchronization function, the data exchange and synchronization function is connected to the system coordination function, the system coordination function is connected to the fault isolation and recovery function, and the fault isolation and recovery function is connected to the warning and response function. The interface standardization function is connected to both the wired communication function and the wireless communication function. The interface standardization function is used for the standardized interfaces and protocols for communicating with other vehicle systems. The data exchange and synchronization function is used for data exchange and synchronization with other vehicle systems. The system coordination function is used to coordinate the operation of each system according to the health status of the lithium battery and the status of other vehicle systems. The fault isolation and recovery function is used to quickly isolate the fault source and take recovery measures when a system fault occurs. The interface standardization function provides standardized interfaces and protocols for communicating with other vehicle systems, ensuring compatibility and interoperability between systems. The data exchange and synchronization function realizes data exchange and synchronization with other vehicle systems, ensuring the real-time and accuracy of information. The system coordination function coordinates the operation of each system according to the health status of the lithium battery and the status of other vehicle systems, improving the overall performance and efficiency of the system. The fault isolation and recovery function can quickly isolate the fault source and take recovery measures when a system fault occurs, reducing the impact of the fault on the system and improving the reliability and stability of the system. At the same time, the connection with the warning and response function enables the system to quickly respond to potential or occurred faults, further enhancing the security of the system.

[0062] Reference Figure 4 As shown, the communication functions include wireless communication function and wired communication function. The wireless communication function is responsible for wireless transmission of data. The wired communication function is used for data interaction between internal units of the system and communication with other vehicle systems. The combination of the wireless communication function and the wired communication function meets the communication requirements in different scenarios. The wired communication function realizes fast data interaction between internal units of the system, improving the overall efficiency of the system.

[0063] Both the wired communication function and the wireless communication function are connected to the total control function, and the total control function controls the communication of the overall system. The wired communication function and the wireless communication function are connected to the data security function, and the data security function encrypts the data transmitted by the wireless communication function and the wired communication function. The data security function encrypts the communication data to ensure the security during data transmission.

[0064] As Figure 5As shown, the state monitoring function is connected to the voltage measurement function, the current measurement function, and the temperature measurement function. The voltage measurement function is used to monitor the voltage of the lithium battery pack in real time. The current measurement function is used to monitor the charge and discharge current of the lithium battery pack. The temperature measurement function is used to monitor the temperature changes inside and outside the battery pack. The voltage measurement function, the current measurement function, and the temperature measurement function are all connected to the total control function. The data of the voltage measurement function, the current measurement function, and the temperature measurement function are transmitted to the total control function for charge and discharge control, balance control, and protection control.

[0065] The voltage measurement function, the current measurement function, and the temperature measurement function are all connected to the data preprocessing function. The data processing function receives the data of each detection function for data preprocessing. The health status prediction function is connected to the total control function. The health status prediction function transmits the health data of the battery to the total control function for display and analysis. The health status prediction function is connected to the data security function. The voltage measurement function, the current measurement function, and the temperature measurement function are all connected to the data security function. The data security function is connected to the total control function to encrypt the data transmitted and received by the total control function.

[0066] Furthermore, as Figure 6 shown, it includes the following steps:

[0067] Step S601: Data collection and preprocessing: Collect various data during the operation of the lithium battery and perform cleaning, screening, and formatting.

[0068] Step S602: Feature extraction and selection: Extract key features from the preprocessed data and select the features that have the greatest impact on the prediction results as the model input.

[0069] Step S603: Real-time prediction and health status evaluation: Use a linear regression prediction model to perform real-time prediction on the health status of the lithium battery and evaluate based on the prediction results.

[0070] Step S604: Feedback and optimization: Verify the prediction results according to the actual usage situation and continuously optimize the linear regression model and the feature selection process.

[0071] The method for predicting the health state of a lithium battery of a vehicle proposed according to an embodiment of the present application can collect various data during the operation of the lithium battery in real time, improve the accuracy of prediction, monitor the fault state of the lithium battery in real time, provide a fault diagnosis report, and send a warning message to the driver or maintenance personnel after detecting a potential fault or confirming a fault, so as to timely discover and handle the faults of the lithium battery, improve the safety and reliability of the vehicle. Moreover, by setting up a linear regression model in the present application, its structure is simple, easy to understand and implement, applicable to a variety of prediction scenarios. At the same time, the model parameters have clear physical meanings and can explain the influence degree of independent variables on dependent variables. In the case of moderate data volume, it has good stability and generalization ability. Thus, it solves the problems in the related technologies. For the method based on a physical model: the model is complex, the calculation amount is large, the measurement accuracy requirements for battery parameters are extremely high, and the accuracy of the model is affected by various factors such as battery aging and temperature change, and it is difficult to accurately reflect the true health state of the battery in practical applications. For the method based on an empirical formula: it is too dependent on experimental data, the generality is poor, lithium batteries of different types and different usage conditions may need to re-establish empirical formulas, and it cannot capture the complex chemical and physical change processes inside the battery, and the prediction accuracy is limited.

[0072] Next, a device for predicting the health state of a lithium battery of a vehicle proposed according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0073] Figure 7 It is a schematic structural diagram of a device for predicting the health state of a lithium battery of a vehicle according to an embodiment of the present application.

[0074] As Figure 7 shown, the device 10 for predicting the health state of a lithium battery of a vehicle includes: a collection module 100, a preprocessing module 200, and a prediction module 300.

[0075] Specifically, the collection module 100 is used to collect at least one of the voltage, current, and temperature of the lithium battery and the speed and mileage of the vehicle.

[0076] The preprocessing module 200 is used to extract the voltage change rate, current peak value, and temperature fluctuation from at least one of the data, and preprocess the voltage change rate, current peak value, and temperature fluctuation to generate preprocessed data.

[0077] The prediction module 300 is used to extract at least one key feature from the preprocessed data, and input the at least one key feature into a pre-constructed linear regression prediction model to use the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result.

[0078] Optionally, in an embodiment of the present application, the lithium battery health state prediction device 10 of the vehicle further includes: a judgment module, a monitoring module, and a prompting module.

[0079] Among them, the judgment module is used to judge whether there is a fault in the lithium battery according to the health state prediction result after using the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generating the health state prediction result.

[0080] The monitoring module is used to monitor the fault state of the lithium battery when there is a fault in the lithium battery, and generate a fault diagnosis report of the lithium battery according to the fault state.

[0081] The prompting module is used to generate at least one fault warning message of the vehicle according to the fault diagnosis report, and prompt the driver of the fault state of the lithium battery according to the at least one fault warning message.

[0082] Optionally, in an embodiment of the present application, the prediction module 300 includes: an integration unit, an evaluation unit, and a prediction unit.

[0083] Among them, the integration unit is used to integrate the lithium battery management system of the vehicle with the lithium battery management system of the target vehicle to generate an integration result.

[0084] The evaluation unit is used to evaluate the health state of the lithium battery based on the integration result according to the overall operation condition data of the vehicle to generate evaluation data.

[0085] The prediction unit is used to adjust the parameters of the pre-constructed linear regression prediction model according to the evaluation data to generate adjusted parameters, and use the adjusted parameters to predict the health state of the lithium battery in real time to generate a health state prediction result.

[0086] Optionally, in an embodiment of the present application, the lithium battery health state prediction device 10 of the vehicle further includes: an encryption module, a storage module, and a communication module.

[0087] Among them, the encryption module is used to encrypt at least one of the voltage, current, and temperature data of the lithium battery after collecting the at least one data to generate encrypted data.

[0088] The storage module is used to store the encrypted data in a preset database, and use the preset database to back up the encrypted data according to a target period to generate backed-up data.

[0089] The communication module is used to transmit the backed-up data to the cloud to communicate with the target vehicle.

[0090] Optionally, in an embodiment of the present application, the preprocessing module 200 includes: a cleaning unit, a screening unit, and a generating unit.

[0091] Among them, a cleaning unit is configured to perform data cleaning on the voltage change rate, current peak value, and temperature fluctuation to generate cleaned data.

[0092] A screening unit is configured to screen the cleaned data to generate data that meets preset normal conditions.

[0093] A generating unit is configured to format the data that meets preset normal conditions to generate preprocessed data.

[0094] It should be noted that the foregoing explanation of the embodiments of the method for predicting the health state of the lithium battery of an automobile also applies to the device for predicting the health state of the lithium battery of the automobile in this embodiment, and will not be elaborated here.

[0095] According to the device for predicting the health state of the lithium battery of an automobile provided by the embodiments of the present application, various data during the operation of the lithium battery can be collected in real time, the accuracy of prediction can be improved, the fault state of the lithium battery can be monitored in real time, a fault diagnosis report can be provided, and a warning message can be sent to the driver or maintenance personnel after detecting a potential fault or confirming a fault, so that the fault of the lithium battery can be discovered and processed in time, and the safety and reliability of the vehicle can be improved. Moreover, by setting a linear regression model in the present application, its structure is simple, easy to understand and implement, applicable to various prediction scenarios, and at the same time, the model parameters have clear physical meanings and can explain the influence degree of independent variables on dependent variables. In the case of moderate data volume, it has good stability and generalization ability. Thus, the problems in the related art are solved. For the method based on a physical model: the model is complex, the calculation amount is large, the measurement accuracy requirements for battery parameters are extremely high, and the accuracy of the model is affected by various factors, such as battery aging, temperature change, etc., and it is difficult to accurately reflect the true health state of the battery in practical applications. For the method based on an empirical formula: it is too dependent on experimental data, the generality is poor, lithium batteries of different types and different usage conditions may require re-establishing empirical formulas, and it is impossible to capture the complex chemical and physical change processes inside the battery, and the prediction accuracy is limited.

[0096] Figure 8 The structure diagram of the vehicle provided by the embodiments of the present application. The vehicle may include:

[0097] A memory 801, a processor 802, and a computer program stored on the memory 801 and executable on the processor 802.

[0098] When the processor 802 executes the program, it implements the method for predicting the health state of the lithium battery of an automobile provided in the foregoing embodiments.

[0099] Furthermore, the vehicle further includes:

[0100] A communication interface 803 for communication between the memory 801 and the processor 802.

[0101] A memory 801 for storing a computer program that can run on a processor 802.

[0102] The memory 801 may include a high-speed RAM memory and may also include a non-volatile memory, such as at least one disk memory.

[0103] If the memory 801, the processor 802, and the communication interface 803 are implemented independently, the communication interface 803, the memory 801, and the processor 802 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 8 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0104] Optionally, in a specific implementation, if the memory 801, the processor 802, and the communication interface 803 are integrated on a chip, the memory 801, the processor 802, and the communication interface 803 can communicate with each other through an internal interface.

[0105] The processor 802 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0106] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method for predicting the health state of a lithium battery of an automobile as described above is implemented.

[0107] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0108] In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0109] Any process or method description shown in a flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or N executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions can be executed in a manner that is not in the order shown or discussed, including in a substantially simultaneous manner according to the functions involved or in the reverse order, which should be understood by those skilled in the art to which the embodiments of this application belong.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definitional sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or N wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, as the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0111] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0112] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0113] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, may exist physically alone for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0114] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for predicting the health state of a lithium battery of an automobile, characterized in that, Including the following steps: Collect at least one piece of data among the voltage, current, and temperature of the lithium battery, and the speed and mileage of the vehicle; Extract the voltage change rate, current peak, and temperature fluctuation from the at least one piece of data, and preprocess the voltage change rate, the current peak, and the temperature fluctuation to generate preprocessed data; Extract at least one key feature from the preprocessed data, and input the at least one key feature into a pre-constructed linear regression prediction model to use the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result.

2. The method according to claim 1, wherein After using the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result, it further includes: Judge whether the lithium battery has a fault according to the health state prediction result; If the lithium battery has a fault, monitor the fault state of the lithium battery, and generate a fault diagnosis report of the lithium battery according to the fault state; Generate at least one fault warning message of the vehicle according to the fault diagnosis report, and prompt the driver of the fault state of the lithium battery according to the at least one fault warning message.

3. The method according to claim 1, characterized in that, The using the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result includes: Integrate the lithium battery management system of the vehicle with the lithium battery management system of the target vehicle to generate an integration result; Based on the integration result, evaluate the health state of the lithium battery according to the overall operation condition data of the vehicle to generate evaluation data; Adjust the parameters of the pre-constructed linear regression prediction model according to the evaluation data to generate adjusted parameters, and use the adjusted parameters to predict the health state of the lithium battery in real time to generate the health state prediction result.

4. The method according to claim 3, wherein After collecting at least one piece of data among the voltage, current, and temperature of the lithium battery, it further includes: Encrypt the at least one piece of data to generate encrypted data; Store the encrypted data in a preset database to use the preset database to back up the encrypted data according to a target period to generate backed-up data; Transmit the backed-up data to the cloud to communicate with the target vehicle.

5. The method according to claim 1, wherein The preprocessing the voltage change rate, the current peak, and the temperature fluctuation to generate preprocessed data includes: Perform data cleaning on the voltage change rate, the current peak, and the temperature fluctuation to generate cleaned data; Screen the cleaned data to generate data that meets preset normal conditions; Format the data that meets the preset normal conditions to generate the preprocessed data.

6. A lithium battery health state prediction device for an automobile, characterized in that, Including: A collection module for collecting at least one piece of data among the voltage, current, and temperature of the lithium battery, and the speed and mileage of the vehicle; A preprocessing module for extracting the voltage change rate, current peak, and temperature fluctuation from the at least one piece of data, and preprocessing the voltage change rate, the current peak, and the temperature fluctuation to generate preprocessed data; A prediction module, configured to extract at least one key feature from the preprocessed data and input the at least one key feature into a pre-constructed linear regression prediction model, so as to use the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result.

7. The device according to claim 6, characterized in that, It further includes: A judgment module, configured to judge whether the lithium battery has a fault according to the health state prediction result after using the pre-constructed linear regression prediction model to predict the health state of the lithium battery in real time and generate a health state prediction result; A monitoring module, configured to monitor the fault state of the lithium battery if the lithium battery has a fault, and generate a fault diagnosis report of the lithium battery according to the fault state; A prompting module, configured to generate at least one fault warning message of the vehicle according to the fault diagnosis report and prompt the driver of the fault state of the lithium battery according to the at least one fault warning message.

8. The device according to claim 6, characterized in that, The prediction module includes: An integration unit, configured to integrate the lithium battery management system of the vehicle and the lithium battery management system of the target vehicle to generate an integration result; An evaluation unit, configured to evaluate the health state of the lithium battery according to the overall operation condition data of the vehicle based on the integration result to generate evaluation data; A prediction unit, configured to adjust the parameters of the pre-constructed linear regression prediction model according to the evaluation data to generate adjusted parameters, and use the adjusted parameters to predict the health state of the lithium battery in real time to generate the health state prediction result.

9. A vehicle, characterized in that, It includes: A memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the method for predicting the health state of the lithium battery of the vehicle according to any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used to implement the method for predicting the health state of the lithium battery of the vehicle according to any one of claims 1-5.

Images